On Mon, Feb 13, 2012 at 09:43:10AM +0000, YAMAMOTO Takashi wrote: > in this particular case, i think that the child does not actually > need to acquire the lock because the parent always keeps it locked. > probably some comments and assertion updates are necessary, tho.
Yeah, will fix it that way for now, but will revisit it for future "extended parallelization" work. Something like: child does rw_tryenter() and releases the parent early if that works. If it fails, it does not get its own lock and releases parent late. Martin